by vbcherepanov · MCP Server · ★ 42
total-agent-memory The only memory layer that learns how you work — not just what you said. Persistent, local memory for AI coding agents: Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph · procedural memory · AST codebase ingest · cross-project analogy · 3D WebGL visualization. []() []() []() [![Docker GHC
| Stars | 42 |
| Forks | 11 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 65.3882738358056/100 |
| Open Issues | 2 |
| Last Updated | 2026-05-26 |
| Created | 2026-02-16 |
| Platforms | browser, claude-code, cli, codex, mcp, python |
| Est. Tokens | ~473k |
These tools work well together with total-agent-memory for enhanced workflows:
Explore other popular mcp server tools:
total-agent-memory is Persistent memory for Claude Code & Codex CLI. Auto-extracted knowledge graph, multi-representation embeddings, 3D WebGL visualization. LongMemEval R@5=97.45%. Self-hosted, Ollama-optional. It is categorized as a MCP Server with 42 GitHub stars.
total-agent-memory is primarily written in Python. It covers topics such as ai-memory, ai-tools, anthropic.
You can find installation instructions and usage details in the total-agent-memory GitHub repository at github.com/vbcherepanov/total-agent-memory. The project has 42 stars and 11 forks, indicating an active community.
total-agent-memory is released under the MIT license, making it free to use and modify according to the license terms.